Psychoacoustic measures of blind audio source separation performance

2008 ◽  
Vol 123 (5) ◽  
pp. 3885-3885
Author(s):  
Mingu Lee ◽  
Inseok Heo ◽  
Nakjin Choi ◽  
Koeng‐Mo Sung
Keyword(s):  
Source Separation ◽  
Separation Performance ◽  
Audio Source Separation

scholarly journals Audio Source Separation using Sparse Representations

2010 ◽  
pp. 246-265 ◽  
Author(s):  
Andrew Nesbit ◽  
Maria G. Jafar ◽  
Emmanuel Vincent ◽  
Mark D. Plumbley
Keyword(s):  
Source Separation ◽  
Feedback System ◽  
Decomposition Methods ◽  
Audio Coding ◽  
Future Research ◽  
Separation Performance ◽  
Audio Source Separation ◽  
Sparse Component Analysis ◽  
Good Signal ◽  
Music Signals

The authors address the problem of audio source separation, namely, the recovery of audio signals from recordings of mixtures of those signals. The sparse component analysis framework is a powerful method for achieving this. Sparse orthogonal transforms, in which only few transform coefficients differ significantly from zero, are developed; once the signal has been transformed, energy is apportioned from each transform coefficient to each estimated source, and, finally, the signal is reconstructed using the inverse transform. The overriding aim of this chapter is to demonstrate how this framework, as exemplified here by two different decomposition methods which adapt to the signal to represent it sparsely, can be used to solve different problems in different mixing scenarios. To address the instantaneous (neither delays nor echoes) and underdetermined (more sources than mixtures) mixing model, a lapped orthogonal transform is adapted to the signal by selecting a basis from a library of predetermined bases. This method is highly related to the windowing methods used in the MPEG audio coding framework. In considering the anechoic (delays but no echoes) and determined (equal number of sources and mixtures) mixing case, a greedy adaptive transform is used based on orthogonal basis functions that are learned from the observed data, instead of being selected from a predetermined library of bases. This is found to encode the signal characteristics, by introducing a feedback system between the bases and the observed data. Experiments on mixtures of speech and music signals demonstrate that these methods give good signal approximations and separation performance, and indicate promising directions for future research.

scholarly journals Integrating Dilated Convolution into DenseLSTM for Audio Source Separation

2021 ◽  
Vol 11 (2) ◽  
pp. 789
Author(s):  
Woon-Haeng Heo ◽  
Hyemi Kim ◽  
Oh-Wook Kwon
Keyword(s):  
Deep Learning ◽  
Speech Signal ◽  
Source Separation ◽  
Series Data ◽  
Separation Performance ◽  
Time Frequency ◽  
Dilated Convolution ◽  
Audio Source Separation ◽  
Music Signal ◽  
Learning Architectures

Herein, we proposed a multi-scale multi-band dilated time-frequency densely connected convolutional network (DenseNet) with long short-term memory (LSTM) for audio source separation. Because the spectrogram of the acoustic signal can be thought of as images as well as time series data, it is suitable for convolutional recurrent neural network (CRNN) architecture. We improved the audio source separation performance by applying the dilated block with a dilated convolution to CRNN architecture. The dilated block has the role of effectively increasing the receptive field in the spectrogram. In addition, it was designed in consideration of the acoustic characteristics that the frequency axis and the time axis in the spectrogram are changed by independent influences such as speech rate and pitch. In speech enhancement experiments, we estimated the speech signal using various deep learning architectures from a signal in which the music, noise, and speech were mixed. We conducted the subjective evaluation on the estimated speech signal. In addition, speech quality, intelligibility, separation, and speech recognition performance were also measured. In music signal separation, we estimated the music signal using several deep learning architectures from the mixture of the music and speech signal. After that, the separation performance and music identification accuracy were measured using the estimated music signal. Overall, the proposed architecture shows the best performance compared to other deep learning architectures not only in speech experiments but also in music experiments.

Blind Complex Source Separation Based on Cyclostationary Statistics

2014 ◽  
Vol 519-520 ◽  
pp. 1051-1056
Author(s):  
Jie Guo ◽  
An Quan Wei ◽  
Lei Tang
Keyword(s):  
Blind Source Separation ◽  
Source Separation ◽  
Separation Performance ◽  
Separation Algorithm ◽  
Complex Signals ◽  
Cyclic Frequency ◽  
Complex Source ◽  
Simulation Results ◽  
Better Than ◽  
Separation Model

This paper analyzed a blind source separation algorithm based on cyclic frequency of complex signals. Under the blind source separation model, we firstly gave several useful assumptions. Then we discussed the derivation of the BSS algorithm, including the complex signals and the normalization situation. Later, we analyzed the complex WCW-CS algorithm, which was compared with NGA, NEASI and NGA-CS algorithms. Simulation results show that the complex WCW-CS algorithm has the best convergence and separation performance. It can also effectively separate mixed image signals, whose performance was better than NGA algorithm.

Sign in / Sign up

Export Citation Format

Share Document